Multicenter External Validation of the Liverpool Uveal Melanoma Prognosticator Online: An OOG Collaborative Study

Deferral of Treatment for Small Choroidal Melanoma and the Risk of Metastasis: An Investigation Using the Liverpool Uveal Melanoma Prognosticator Online (LUMPO)

BACKGROUND

We estimated metastatic-death risk when the treatment of small choroidal melanomas is deferred until growth is observed.

METHODS

In 24 patients with choroidal melanoma (median diameter 5.85 mm), the exponential growth rate estimated by a mixed-effects model was 4.3% per year. Using the Liverpool Uveal Melanoma Prognosticator Online v.3 (LUMPO3), we measured changes in 15-year metastatic and non-metastatic death risks according to whether the tumor is treated immediately or after observing growth 4 or 12 months later, considering age, sex, and metastasis predictors.

RESULTS

In 40-year-old females with 10 mm, disomy 3 and monosomy 3 choroidal melanomas (prevalence 16%), the 15-year absolute risks of metastatic death are 4.2% and 76.6%, respectively, increasing after a 4-month delay by 0.0% and 0.2% and by 3.0% and 2.3% with tumor growth rates of 5.0% and 20.0%, respectively. With 12-month delays, these risks increase by 0.0% and 0.5% and by 1.0% and 7.1%, respectively. Increases in metastatic-death risk are less with smaller tumors and with a higher risk of non-metastatic death.

CONCLUSIONS

Deferring treatment of choroidal melanomas until documentation of growth may delay iatrogenic visual loss by months or years and is associated with minimal increase in metastatic mortality, at least with small tumors with usual growth rates of up to 40% per year.

Updates in the Management of Uveal Melanoma

ABSTRACT

Uveal melanoma (UM), arising from intraocular melanocytes, poses a complex clinical challenge with a substantial risk of distant metastasis, often to the liver. Molecular profiling, encompassing genetic, cytogenetic, gene expression, and immunological subsets, plays a pivotal role in determining prognoses. The evolving landscape includes promising systemic treatments, such as tebentafusp, a novel immune-modulating bispecific fusion protein, and targeted therapies. Combined regional and systemic approaches, including immune checkpoint inhibitors and innovative liver-directed therapy, are also under investigation. Although recent progress has improved outcomes, ongoing research aims to address the unique challenges of UM and develop effective therapies, particularly for HLA-A*02:01-negative patients who represent a significant unmet medical need. This review comprehensively discusses the molecular characteristics of UM, risk stratification methods, and the current and future spectrum of regional and systemic therapeutic modalities.

Association of BARD1 and BRIP1 Gene Polymorphisms with the Risk of Uveal Melanoma

Considering the limited information about the role of hereditary predisposition to the development of uveal melanoma, we have performed an analysis of the frequencies of BARD1 (rs1048108, rs2229571, rs2070094) and BRIP1 (rs4986764) gene polymorphisms in patients with uveal melanoma and benign choroidal nevus in comparison with healthy volunteers (control). It has been found that the minor alleles of BRIP1 rs4986764 and BARD1 rs2070094 polymorphisms, as well as the homozygosity of T allele at the BARD1 rs1048108 locus are common genetic markers for the predisposition to uveal melanoma and benign choroidal nevus, while the homozygous genotype GG for the BARD1 rs2229571 polymorphism is a specific marker for the predisposition to uveal melanoma and progressive choroidal nevus. We have also found that the heterozygous genotype at BARD1 rs1048108 polymorphic locus is a specific marker for protection against uveal melanoma and progressive choroidal nevus. Thus, our results indicate the advisability of studying polymorphisms of the BARD1 gene (rs1048108, rs2229571, and rs2070094) and the BRIP1 gene (rs4986764) in patients with uveal melanoma and progressive choroidal nevus. The obtained findings can be used for forming risk groups, prevention of uveal melanoma, and differential diagnosis of intraocular neoplasms.

Sensitivity and Specificity of Different Prognostic Systems in Guiding Surveillance for Metastases in Uveal Melanoma

Uveal melanoma (UM) metastasises in ~50% of patients, most frequently to the liver. Surveillance imaging can provide early detection of hepatic metastases; however, guidance regarding UM patient risk stratification for surveillance is unclear. This study compared sensitivity and specificity of four current prognostic systems, when used for risk stratification for surveillance, on patients treated at the Liverpool Ocular Oncology Centre (LOOC) between 2007-2016 (n = 1047). It found that the Liverpool Uveal Melanoma Prognosticator Online III (LUMPOIII) or Liverpool Parsimonious Model (LPM) offered greater specificity at equal levels of sensitivity than the American Joint Committee on Cancer (AJCC) system or monosomy 3 alone, and suggests guidance to achieve 95% sensitivity and 51% specificity (i.e., how to detect the same number of patients with metastases, while reducing the number of negative scans). For example, 180 scans could be safely avoided over 5 years in 200 patients using the most specific approach. LUMPOIII also offered high sensitivity and improved specificity over the AJCC in the absence of genetic information, making the result relevant to centres that do not perform genetic testing, or where such testing is inappropriate or fails. This study provides valuable information for clinical guidelines for risk stratification for surveillance in UM.

Advances in the clinical management of uveal melanoma

Melanomas arising in the uveal tract of the eye are a rare form of the disease with a biology and clinical phenotype distinct from their more common cutaneous counterparts. Treatment of primary uveal melanoma with radiotherapy, enucleation or other modalities achieves local control in more than 90% of patients, although 40% or more ultimately develop distant metastases, most commonly in the liver. Until January 2022, no systemic therapy had received regulatory approval for patients with metastatic uveal melanoma, and these patients have historically had a dismal prognosis owing to the limited efficacy of the available treatments. A series of seminal studies over the past two decades have identified highly prevalent early, tumour-initiating oncogenic genomic aberrations, later recurring prognostic alterations and immunological features that characterize uveal melanoma. These advances have driven the development of a number of novel emerging treatments, including tebentafusp, the first systemic therapy to achieve regulatory approval for this disease. In this Review, our multidisciplinary and international group of authors summarize the biology of uveal melanoma, management of primary disease and surveillance strategies to detect recurrent disease, and then focus on the current standard and emerging regional and systemic treatment approaches for metastatic uveal melanoma.

Cytogenetic Abnormalities for Predicting the Risk of Metastases in Choroidal and Ciliary Body Melanoma

Purpose

Choroidal melanoma (CM) and ciliary body melanoma (CBM) are the two most common subtypes of uveal melanoma. Starting from the observation that CBM tends to have a higher metastatic potential than CM, we hypothesized that specific cytogenetic abnormalities could be associated with tumor location - reflecting distinct genetic signatures that would drive the risk of distant spread.

Methods

Chromosomal alterations were investigated by molecular cytogenetic techniques in 217 and 97 patients with CM and CBM, respectively. Cox proportional hazards regression analysis was used to identify the independent predictors of distant metastasis.

Results

Patients with CBM had larger tumor sizes (P < 0.001), higher disease stages (P < 0.001), and more frequently showed distant metastasis (P = 0.002) than those with CM. On analyzing the entire study cohort, we found that specific chromosomal alterations - including chromosome 8p loss (P < 0.001), 1p loss (P < 0.001), and monosomy 3 (P < 0.005) - were independent predictors of distant metastasis. Based on a decision-tree learning algorithm, we identified three specific subgroups of patients with uveal melanoma at high risk of distant spread. Monosomy 3 occurred significantly more frequently in patients with T3 CBM tumors.

Conclusions

Specific cytogenetic abnormalities - including chromosome 8p loss, 1p loss, and monosomy 3 - are independent risk factors for distant metastasis in uveal melanoma. Larger tumor size at presentation and monosomy 3 contribute to a higher metastatic risk in patients with CBM.

Tebentafusp for the treatment of HLA-A*02:01-positive adult patients with unresectable or metastatic uveal melanoma

INTRODUCTION

: Metastatic uveal melanoma is associated with poor prognosis and few treatment options. Tebentafusp recently became the first FDA-approved agent for metastatic uveal melanoma.

AREAS COVERED

In this review, we describe the mechanism of action of tebentafusp as well as preclinical data showing high tumor specificity of the drug. We also review promising early phase trials in which tebentafusp demonstrated activity in metastatic uveal melanoma patients with an acceptable toxicity profile that included cytokine-mediated, dermatologic-related, and liver-related adverse events. Finally, we summarize findings from a pivotal phase III randomized trial in which tebentafusp demonstrated significant improvement in overall survival in comparison with investigator choice therapy.

EXPERT OPINION

Tebentafusp has transformed the treatment paradigm for metastatic uveal melanoma and should be the preferred frontline agent for most HLA-A*0201 positive patients. However, patients with rapidly progressing disease or high tumor benefit may not derive the same benefit. Areas of future study should focus on its role in the adjuvant setting as well as strategies to improve efficacy of tebentafusp in the metastatic setting.

A Novel and Easy-to-Promote Prognostic Model for Patients With Uveal Melanoma

Purpose

To establish an easy and widely applicable prognostic prediction model for uveal melanoma (UM) based on a Chinese population.

Patients and Methods

A total of 295 consecutive cases treated at the Eye & ENT Hospital of Fudan University were included as the primary cohort, and 256 cases were included in the validation cohorts from two external Caucasian databases. Clinicopathological data were collected retrospectively, and nomogram models were formulated based on multivariable analysis. The concordance index (C-index), AUC (area under the Receiver Operating Characteristic, ROC curve), and Brier score were calculated and compared.

Results

Based on the training cohort, a nomogram model was established with five relevant variables: age, tumor size, ciliary body involvement, non-spindle cell type and extra-scleral extension. The C-index was 0.737, the 3- and 5-year AUCs were 0.767 and 0.742, and the Brier scores for 3- and 5-year survival were 0.082 and 0.129, respectively, which showed superior prediction compared to that of the Tumor, Node and Metastasis staging system. The model also displayed good discrimination and calibration in the external validation cohorts. By risk stratification, patients could be divided into low- and high-risk groups, and the overall survival curves displayed significant differences in the training and validation cohorts.

Conclusion

Our nomogram model was simple and accurate at predicting the overall survival of patients with UM. It was established based on Asian patients and proved suitable for Caucasian patients; thus, it has a wide range of potential applications, especially for patients living in less medically developed countries and regions.

A Retrospective Analysis of 10 Years of Liver Surveillance Undertaken in Uveal Melanoma Patients Treated at the Supraregional "Liverpool Ocular Oncology Centre", UK

Simple Summary

Around 45% of patients with uveal melanoma (UM) develop liver metastases on average 3 years after diagnosis of the primary tumour. After clinical detection of metastases, median patient survival is approximately one year. Early identification of metastases through liver surveillance is important so that targeted treatment can benefit affected patients, aiming to prolong their survival. The aim of our retrospective study was to investigate and correlate the characteristics of UM patients diagnosed and treated at a UK supraregional referral center, the Liverpool Ocular Oncology Centre (LOOC), and who were included in the Centre’s liver screening programs for screening for liver metastases. “Real-world” data on the frequency of liver screening in patients after diagnosis and treatment of primary UM are lacking. Through the liver screening program, we found that metastases were detected in 37% of the 615 UM patients studied. A new output based on the prognostic indices of the Liverpool Uveal Melanoma Prognosticator Online version 3 (LUMPO3) model was fitted to the dataset of these patients and accurately estimated the time of onset of metastases.

Abstract

Purpose: To determine liver screening frequency and modality in UM patients following primary treatment, and the characteristics of detected metastases. Methods: A 10-year retrospective study of 615 UM patients undergoing liver surveillance in Liverpool. Information was collected from liver scan reports of these patients. Results: Of 615 UM patients analyzed, there were 337 men (55%) and 278 women (45%). Median age at primary treatment was 61 years (range, 22–94). At study end, median follow-up was 5.1 years, with 375 patients (61%) alive and 240 deceased (39%). Of the deceased patients, 187 (78%) died due to metastatic UM; 24 (10%) deaths were due to other causes; and 29 (12%) patients died of unknown conditions. In total, 3854 liver scans were performed in the 615 UM patients, with a median of 6.2 scans per patient (range, 1–40). Liver MRI was most frequently performed (62.8%). In total, 229 (37%) UM patients developed metastases during the study period: 150 were detected via liver surveillance and 79 were observed post-mortem. Conclusions: Metastatic UM onset is related to the size and genetic profiles of the primary UM, and can be predicted using the model LUMPO3. Regular liver surveillance allowed for timely detection of metastases, and through metastasectomy can lead to prolongation of life in some patients.

Vascular Lakes in Uveal Melanoma and Their Association With Outcome

Purpose

Prognostic predictors in uveal melanoma (UM) consist of clinical, histomorphologic, and genetic features. Vascular lakes (VLs) are immature blood vessels within UM with unknown significance for metastatic risk.

Methods

A clinically well-phenotyped cohort of 136 hematoxylin and eosin–stained slides of UM enucleation specimens were retrospectively analyzed on scanned whole-slide images. These were annotated for VL in QuPath, assessing VL number and area. Using SPSS (V27.0), the Mann–Whitney U test and Cox regression were applied to evaluate whether there was any correlation between VL number and area within the tumor (VL-TA) compared with other prognostic parameters and patient survival times.

Results

UMs with monosomy 3 (M3) have significant differences in their VL numbers (P = 0.008) and VL-TA ratios (P = 0.002) compared with disomy 3-UM. Nuclear BAP1-negative (nBAP1^–) UMs have significant differences in their VL-TA ratio (P = 0.002) compared to nBAP1⁺ UMs. Survival times of patients with UM with epithelioid-celled tumors varied depending on their VL-TA ratio (P = 0.057). Similarly, in M3-UM, significant differences in survival (P = 0.009) were seen in patients, depending on VL number. Finally, patients with UM with shorter overall survival showed significant differences in their tumor VL-TA ratios (P = 0.043) and the number of VLs present (P = 0.002) than patients with UM who had longer survival.

Conclusions

Our pilot data suggest that VL-TA is an additional poor prognostic parameter in UM.

Translational Relevance

Digital analysis of UM can be easily performed to assess various prognostic parameters. Our pilot study demonstrates that UM-VL could be combined with other parameters to determine metastatic risk of patients with UM.

Prognosis Prediction of Uveal Melanoma After Plaque Brachytherapy Based on Ultrasound With Machine Learning

INTRODUCTION

Uveal melanoma (UM) is the most common intraocular malignancy in adults. Plaque brachytherapy remains the dominant eyeball-conserving therapy for UM. Tumor regression in UM after plaque brachytherapy has been reported as a valuable prognostic factor. The present study aimed to develop an accurate machine-learning model to predict the 4-year risk of metastasis and death in UM based on ocular ultrasound data.

MATERIAL AND METHODS

A total of 454 patients with UM were enrolled in this retrospective, single-center study. All patients were followed up for at least 4 years after plaque brachytherapy and underwent ophthalmologic evaluations before the therapy. B-scan ultrasonography was used to measure the basal diameters and thickness of tumors preoperatively and postoperatively. Random Forest (RF) algorithm was used to construct two prediction models: whether a patient will survive for more than 4 years and whether the tumor will develop metastasis within 4 years after treatment.

RESULTS

Our predictive model achieved an area under the receiver operating characteristic curve (AUC) of 0.708 for predicting death using only a one-time follow-up record. Including the data from two additional follow-ups increased the AUC of the model to 0.883. We attained AUCs of 0.730 and 0.846 with data from one and three-time follow-up, respectively, for predicting metastasis. The model found that the amount of postoperative follow-up data significantly improved death and metastasis prediction accuracy. Furthermore, we divided tumor treatment response into four patterns. The D(decrease)/S(stable) patterns are associated with a significantly better prognosis than the I(increase)/O(other) patterns.

CONCLUSIONS

The present study developed an RF model to predict the risk of metastasis and death from UM within 4 years based on ultrasound follow-up records following plaque brachytherapy. We intend to further validate our model in prospective datasets, enabling us to implement timely and efficient treatments.

Survival analysis following enucleation for uveal melanoma

OBJECTIVES

To determine survival outcomes following enucleation for uveal melanoma. To compare these outcomes with the 8th edition AJCC classification and determine the influence of cytogenetics, using Fluorescent in situ Hybridisation (FISH), on survival. To determine whether failure to gain sufficient sample for cytogenetics using Fine Needle Aspiration Biopsy (FNAB) correlates with survival.

SUBJECTS/METHODS

All patients undergoing primary enucleation for uveal melanoma at Moorfields Eye Hospital between 2012 and 2015 were included. Clinical, pathological, cytological and survival data were analysed for all patients.

RESULTS

In total, 155 subjects were included. Mean age at enucleation was 65.9 years (SD 14.13). 88 (56.8%) patients died at a mean of three (SD 1.9) years following enucleation. Of these, 52 (33.5%) died from metastatic melanoma, 16 (10.3%) from other causes and 20 (12.9%) causes of death were unknown. Cumulative incidence analysis demonstrated AJCC grade, chromosome 8q gain and monosomy three all predict metastatic mortality. The greatest 5-year mortality rate (62%, SD10.1%) was in those with both chromosome abnormalities and AJCC stage III (Stage IV patients excluded due to low numbers). Largest basal diameter and chromosome status, both independently (p = 0.02 and p < 0.001) predicted metastatic mortality on multivariable regression analysis. Those who had an insufficient sample of cells gained during FNAB (n = 16) had no different prognosis.

CONCLUSIONS

This study confirms, in this population, the poor survival of patients enucleated for uveal melanomas. It confirms the prognostic utility of adding AJCC grade to cytogenetic information. It demonstrates that the lack of sample in patients undergoing FNAB is not related to prognosis.

Small High-Risk Uveal Melanomas Have a Lower Mortality Rate

Simple Summary

The current paradigm concerning metastatic spread in uveal melanoma is that the critical point for dissemination occurs prior to presentation and that treatment of the primary tumor does not change outcome. However, we show that patients with small uveal melanomas with genetic characteristics typical for high risk for metastatic disease have a lower mortality rate from metastatic disease, if treated earlier. Our data demonstrate that such small melanomas are potentially lethal (like larger tumors), but that there is a window of opportunity to prevent life-threatening metastatic spread if actively treated, rather than being monitored, as is often done currently.

Abstract

Our aim was to determine whether size impacts on the difference in metastatic mortality of genetically high-risk (monosomy 3) uveal melanomas (UM). We undertook a retrospective analysis of data from a patient cohort with genetically characterized UM. All patients treated for UM in the Liverpool Ocular Oncology Centre between 2007 and 2014, who had a prognostic genetic tumor analysis. Patients were subdivided into those with small (≤2.5 mm thickness) and large (>2.5 mm thickness) tumors. Survival analyses were performed using Gray rank statistics to calculate absolute probabilities of dying as a result of metastatic UM. The 5-year absolute risk of metastatic mortality of those with small monosomy 3 UM was significantly lower (23%) compared to the larger tumor group (50%) (p = 0.003). Small disomy 3 UM also had a lower absolute risk of metastatic mortality (0.8%) than large disomy 3 UM (6.4%) (p = 0.007). Hazard rates showed similar differences even with lead time bias correction estimates. We therefore conclude that earlier treatment of all small UM, particularly monosomy 3 UM, reduces the risk of metastatic disease and death. Our results would support molecular studies of even small UM, rather than ‘watch-and-wait strategies’.

Application of Multimodal and Molecular Imaging Techniques in the Detection of Choroidal Melanomas

Choroidal melanomas are the most common ocular malignant tumors worldwide. The onset of such tumors is insidious, such that affected patients often have no pain or obvious discomfort during early stages. Notably, enucleation is required for patients with a severe choroidal melanoma, which can seriously impact their quality of life. Moreover, choroidal melanomas metastasize early, often to the liver; this eventually causes affected patients to die of liver failure. Therefore, early diagnosis of choroidal melanomas is extremely important. Unfortunately, an early choroidal melanoma is easily confused with a choroidal nevus, which is the most common benign tumor of the eye and does not often require surgical treatment. This review discusses recent advances in the use of multimodal and molecular imaging to identify choroidal melanomas and choroidal nevi, detect early metastasis, and diagnose patients with choroidal melanomas.

Cost-utility analysis of a decade of liver screening for metastases using the Liverpool Uveal Melanoma Prognosticator Online (LUMPO)

This paper outlines a method for cost-utility analysis of liver screening for metastases in patients with posterior uveal melanoma (UM). A semiparametric model of the cumulative incidence of onset of liver metastases was fitted to a retrospective data set of 615 subjects with clinical follow-up with respect to liver surveillance imaging and outcome. The model was internally validated via bootstrap resampling in terms of its discrimination and calibration performance. Receiver operating characteristics (ROC) were derived at different time points. The discrimination performances are consistent across time. The area under the ROC curve at 5 years post treatment was 0.85 [95% CI: 0.81-0.88]. A goodness-of-fit test gives χ²(10)=5.3,p=0.9 demonstrating no evidence against the null hypothesis of zero difference between observed and expected onset of metastatic events. Results showed that at 80% sensitivity, 87% of UM patients will avoid unnecessary radiological scans. This provides potential cost savings of between £46,000 and £97,000 per year to the National Health Service assuming 600 new cases per year.

Patients presenting with metastases: stage IV uveal melanoma, an international study

OBJECTIVE

To analyse ocular and systemic findings of patients presenting with systemic metastasis.

METHODS AND ANALYSIS

It is an international, multicentre, internet-enabled, registry-based retrospective data analysis. Patients were diagnosed between 2001 and 2011. Data included: primary tumour dimensions, extrascleral extension, ciliary body involvement, American Joint Committee on Cancer (AJCC)-tumour, node, metastasis staging, characteristics of metastases.

RESULTS

Of 3610 patients with uveal melanoma, 69 (1.9%; 95% CI 1.5 to 2.4) presented with clinical metastasis (stage IV). These melanomas originated in the iris, ciliary body and choroid in 4%, 16% and 80% of eyes, respectively. Using eighth edition AJCC, 8 (11%), 20 (29%), 24 (35%), and 17 (25%) belonged to AJCC T-categories T1-T4. Risk of synchronous metastases increased from 0.7% (T1) to 1.5% (T2), 2.6% (T3) and 7.9% (T4). Regional lymph node metastases (N1a) were detected in 9 (13%) patients of whom 6 (67%) had extrascleral extension. Stage of systemic metastases (known for 40 (59%) stage IV patients) revealed 14 (35%), 25 (63%) and 1 (2%) had small (M1a), medium-sized (M1b) and large-sized (M1c) metastases, respectively. Location of metastases in stage IV patients were liver (91%), lung (16%), bone (9%), brain (6%), subcutaneous tissue (4%) and others (5%). Multiple sites of metastases were noted in 24%. Compared with the 98.1% of patients who did not present with metastases, those with synchronous metastases had larger intraocular tumours, more frequent extrascleral extension, ciliary body involvement and thus a higher AJCC T-category.

CONCLUSIONS

Though higher AJCC T-stage was associated with risk for metastases at diagnosis, even small T1 tumours were stage IV at initial presentation. The liver was the most common site of metastases; however, frequent multiorgan involvement supports initial whole-body staging.

Applying Single-Cell Technology in Uveal Melanomas: Current Trends and Perspectives for Improving Uveal Melanoma Metastasis Surveillance and Tumor Profiling

Uveal melanoma (UM) is the most common primary adult intraocular malignancy. This rare but devastating cancer causes vision loss and confers a poor survival rate due to distant metastases. Identifying clinical and molecular features that portend a metastatic risk is an important part of UM workup and prognostication. Current UM prognostication tools are based on determining the tumor size, gene expression profile, and chromosomal rearrangements. Although we can predict the risk of metastasis fairly accurately, we cannot obtain preclinical evidence of metastasis or identify biomarkers that might form the basis of targeted therapy. These gaps in UM research might be addressed by single-cell research. Indeed, single-cell technologies are being increasingly used to identify circulating tumor cells and profile transcriptomic signatures in single, drug-resistant tumor cells. Such advances have led to the identification of suitable biomarkers for targeted treatment. Here, we review the approaches used in cutaneous melanomas and other cancers to isolate single cells and profile them at the transcriptomic and/or genomic level. We discuss how these approaches might enhance our current approach to UM management and review the emerging data from single-cell analyses in UM.

Piloting a Deep Learning Model for Predicting Nuclear BAP1 Immunohistochemical Expression of Uveal Melanoma from Hematoxylin-and-Eosin Sections

Background

Uveal melanoma (UM) is the most common primary intraocular malignancy in adults. Monosomy 3 and BAP1 mutation are strong prognostic factors predicting metastatic risk in UM. Nuclear BAP1 (nBAP1) expression is a close immunohistochemical surrogate for both genetic alterations. Not all laboratories perform routine BAP1 immunohistochemistry or genetic testing, and rely mainly on clinical information and anatomic/morphologic analyses for UM prognostication. The purpose of our study was to pilot deep learning (DL) techniques to predict nBAP1 expression on whole slide images (WSIs) of hematoxylin and eosin (H&E) stained UM sections.

Methods

One hundred forty H&E-stained UMs were scanned at 40 × magnification, using commercially available WSI image scanners. The training cohort comprised 66 BAP1⁺ and 74 BAP1⁻ UM, with known chromosome 3 status and clinical outcomes. Nonoverlapping areas of three different dimensions (512 × 512, 1024 × 1024, and 2048 × 2048 pixels) for comparison were extracted from tumor regions in each WSI, and were resized to 256 × 256 pixels. Deep convolutional neural networks (Resnet18 pre-trained on Imagenet) and auto-encoder-decoders (U-Net) were trained to predict nBAP1 expression of these patches. Trained models were tested on the patches cropped from a test cohort of WSIs of 16 BAP1⁺ and 28 BAP1⁻ UM cases.

Results

The trained model with best performance achieved area under the curve values of 0.90 for patches and 0.93 for slides on the test set.

Conclusions

Our results show the effectiveness of DL for predicting nBAP1 expression in UM on the basis of H&E sections only.

Translational Relevance

Our pilot demonstrates a high capacity of artificial intelligence-related techniques for automated prediction on the basis of histomorphology, and may be translatable into routine histology laboratories.

Parsimonious Models for Predicting Mortality from Choroidal Melanoma

Purpose

To develop parsimonious models for estimating metastasis mortality in patients with choroidal melanoma for situations where use of the Liverpool Uveal Melanoma Prognosticator Online (LUMPO) or Tumor, Node, Metastasis (TNM) staging system is not possible.

Methods

A backward-selection algorithm identified largest basal tumor diameter (LBTD) and chromosome 3 status (C3S) as the most informative predictors of metastatic death. We defined two prognostic models, based on LBTD with or without known C3S, that took into account competing risks of death from other causes by using the Aalen estimator. The bootstrap procedure was used to estimate discrimination accuracy, expressed by the C-index.

Results

The cohort was comprised of 8348 patients with choroidal melanoma, 4174 of whom had known chromosome 3 status; of the 1553 deaths that occurred among these patients, 956 were attributed to metastasis. For LBTD with or without known C3S, the metastatic-death-specific C-indices at 2, 5, and 10 years were 0.85, 0.85, and 0.84 and 0.79, 0.77, and 0.74, respectively, as compared with 0.81, 0.79, and 0.76 for Kaplan–Meier prognostication using the 8th edition of the TNM staging system.

Conclusions

We have developed parsimonious models for predicting the absolute risks of metastatic death from choroidal melanoma that take into account competing causes of death and which compare favorably with the current version of the TNM staging system. There is a need for further studies to validate the use of these models in situations where use of the TNM or LUMPO is not possible.

MicroRNAs and Uveal Melanoma: Understanding the Diverse Role of These Small Molecular Regulators

Uveal melanoma (UM) is a rare tumour of the eye, characterised by a high propensity to metastasise in half of all patients, most frequently to the liver. Although there are effective treatment options for the primary tumour, once metastasis has occurred prognosis is poor, with overall survival limited to months. Currently, there are no effective treatments for metastatic UM, despite the tumour having a well-defined signalling pathway to which many therapies have been directed. In an effort to develop novel treatment approaches, understanding the role of other signalling molecules, such as microRNAs, is fundamental. MicroRNAs (miRNAs) are small non-coding RNA molecules involved in posttranscriptional gene regulation, resulting in reduced target gene expression and subsequent protein translation. In UM, several dysregulated miRNAs have been proposed to play a functional role in disease progression, whereas others have been put forward as clinical biomarkers of high-risk disease following isolation from blood, plasma and exosomes. Most recently, analyses of large datasets have identified promising prognostic miRNA signatures and panels. This review navigates the plethora of aberrant miRNAs disclosed so far in UM, and maps these to signalling pathways, which could be targeted in future therapies for the disseminated disease.

Uveal melanoma pathobiology: Metastasis to the liver

Uveal melanoma (UM) is a type of intraocular tumor with a propensity to disseminate to the liver. Despite the identification of the early driver mutations during the development of the pathology, the process of UM metastasis is still not fully comprehended. A better understanding of the genetic, molecular, and environmental factors participating to its spread and metastatic outgrowth could provide additional approaches for UM treatment. In this review, we will discuss the advances made towards the understanding of the pathogenesis of metastatic UM, summarize the current and prospective treatments, and introduce some of the ongoing research in this field.

Targeted Next-Generation Sequencing of 117 Routine Clinical Samples Provides Further Insights into the Molecular Landscape of Uveal Melanoma

Uveal melanoma (UM) has well-characterised somatic copy number alterations (SCNA) in chromosomes 1, 3, 6 and 8, in addition to mutations in GNAQ, GNA11, CYSLTR2, PLCB4, BAP1, SF3B1 and EIF1AX, most being linked to metastatic-risk. To gain further insight into the molecular landscape of UM, we designed a targeted next-generation sequencing (NGS) panel to detect SCNA and mutations in routine clinical UM samples. We compared hybrid-capture and amplicon-based target enrichment methods and tested a larger cohort of primary UM samples on the best performing panel. UM clinical samples processed either as fresh-frozen, formalin-fixed paraffin embedded (FFPE), small intraocular biopsies or following irradiation were successfully profiled using NGS, with hybrid capture outperforming the PCR-based enrichment methodology. We identified monosomy 3 (M3)-UM that were wild-type for BAP1 but harbored SF3B1 mutations, novel frameshift deletions in SF3B1 and EIF1AX, as well as a PLCB4 mutation outside of the hotspot on exon 20 coinciding with a GNAQ mutation in some UM. We observed samples that harboured mutations in both BAP1 and SF3B1, and SF3B1 and EIF1AX, respectively. Novel mutations were also identified in TTC28, KTN1, CSMD1 and TP53BP1. NGS can simultaneously assess SCNA and mutation data in UM, in a reliable and reproducible way, irrespective of sample type or previous processing. BAP1 and SF3B1 mutations, in addition to 8q copy number, are of added importance when determining UM patient outcome.